Search

This paper presents a new method for tracking a zigzag maneuvering target by compensat- ing for the positional error of the target. The positional difference between the measured and predicted points is separated into acceleration and noise. Fuzzy c-means (FCM) clustering is utilized as an adap- tive method for noise separation. Approximating acceleration is determined by the membership func- tion of the FCM. The approximated acceleration is used to compensate for the tracking error. The pro- cedures of the proposed algorithm can be implemented as an on-line system. Finally, some examples are provided to show the effectiveness of the proposed algorithm.

The effort to detect a target conflicts with the covertness in anti-submarine warfare. The underwater detection rate is extremely low and sound waves are the only detection method unlike the airborne operational environment. The data of an underwater target based on noise levels are more difficult to interpret when the acceleration inputs are included. Hence, the authors propose a complementary algorithm for the tracking problem in an active sonar system. The bearing-range data of the target yield the measurement residuals, and the residuals are used as inputs to the clustering method. The clustering method estimates the acceleration and the noise level. The estimates aid in positional compensation and enhance the tracking performance. The fuzzy c-means clustering is utilised for the clustering and maintains the filter sustainable. Finally, some examples are provided to show the effectiveness of the proposed method.

This study proposes a smart tracking model with multiple structures. To achieve optimal performance, an ideal tracking system should maintain contact with the target and constantly update its tracking data. One of the major problems to consider arises from the target motion uncertainty. Although the variance of the overall noise is time-varying and may reduce tracking efficiency, it is difficult to adaptively approximate this uncertainty. To solve these computational problems, a variety of techniques have been studied, and the adaptive interacting multiple model has shown the best result. However, predefined sub-models with different conditions for multiple models are required. Moreover, the acceleration intervals for different acceleration levels should be determined in advance. To alleviate these problems, the authors propose a multiple-structured smart tracking algorithm which properly separates the acceleration from the overall noise by fuzzy c-means clustering. The filter in the algorithm recognises the manoeuvring target as if it does not include the acceleration input, and precisely tracks the target with multiple structures. This study focuses on the acceleration causing the uncertainty and three-dimensional (3D) motion of the real target motion in the tracking problem. Finally, a 3D cruise missile example is provided to show the effectiveness of the proposed algorithm.

This paper presents the smart interacting multiple model (SIMM) using the concept of predicted point and maximum noise level. Maximum noise level means the largest value of the mere noises. We utilize the positional difference between measured point and predicted point as acceleration. Comparing this acceleration with the maximum noise level, we extract the acceleration to recognize the characteristics of the target. To estimate the acceleration, we propose an optional algorithm utilizing the proposed method and the Kalman filter (KF) selectively. Also, for increasing the effect of estimation, the weight given at each sub-filter of the interacting multiple model (IMM) structure is varying according to the rate of noise scale. All the procedures of the proposed algorithm can be implemented by an on-line system. Finally, an example is provided to show the effectiveness of the proposed algorithm.

This paper proposes a new approach on nonlinear maneuvering target tracking. In this paper, proposed algorithm is the Kalman filter based on the adaptive interactive multiple model using the concept of predicted impact point and utilize modified Kalman filter regarding the error between measurement position and predicted impact point. The unknown target acceleration is regarded as an additional process noise to the target model, and each sub-model is characterized in accordance with the valiance of the overall process noise which is obtained on the basis of each acceleration interval. To compensate the decreasing performance of Kalman filter in nonlinear maneuver, we construct optional algorithm to utilize proposed method or Kalman filter selectively. To effectively estimate the acceleration during the target maneuvering, the rapid increase of the noise scale is recognized as the acceleration to be used in maneuvering target`s movement equation. And a few examples are presented to show suggested algorithm`s executional potential.

For the covertness in modern anti-submarine warfare (ASW), a sonar system has been evolved to the bi-static type. However, it is difficult to get the recognizable error coefficients at any time with clear mathematical definition for the sonar model. To resolve the dynamics accompanied with the error component, we should deal with heterogeneous, complementary fusion of information in order to enable robust target detection, classification, localization, and tracking. In the tracking point of view, we concentrate on the increment of tracking error occurred from the target's maneuvering owing to the acceleration. From the measurement residual, compensating acceleration by merging the filter with fuzzy c-means (FCM) clustering is proposed. Finally, a example is provided to show the effectiveness of the proposed algorithm.

This paper presents an intelligent tracking method for nonlinear maneuvering target by compartmentalizing external noises of 3D maneuvering target. Proposed method makes the filter recognize the maneuvering target as linear one by separating acceleration properly from the overhaul noises. For achieving that, we use the particle swam optimization-fuzzy c-means (PSO-FCM) clustering as the criteria of methodology. The positional difference between measured point and predicted one is separated into acceleration and noise. Compartmentalized external noises plays the role of acceleration in accordance with assigned position and its quantity. Proposed algorithm makes approximated acceleration to be compensated and approximated noise is filtered by Kalman filter (KF). To depict the real maneuvering target and track the target with unlimited condition, we handle 3D dynamic model. Finally, some examples are provided to show the effectiveness of the proposed algorithm.